Moderate Pruning

Moderate Pruning is a pruning strategy in machine learning that belongs to the class of model compression techniques and is distinguished by removing an intermediate proportion of redundant or less significant parameters—typically between 30% and 70%—to balance model efficiency and performance retention.

12

Publications

290

Citations

57

Authors

20

Institutions

Publications per year

2017–2026

4

Authors

57

  1. ZD
    Zhen‐Yu Du

    East China Normal University, China

    2 publications · 59 citations

    2

    h-index

  2. GG
    Gary G. Grove

    Washington State University, United States

    1 publications · 41 citations

    1

    h-index

  3. GH
    G. Haseeb

    1 publications · 16 citations

    1

    h-index

  4. JL
    Joanna L. Woods

    Oregon State University, United States

    1 publications · 41 citations

    1

    h-index

  5. MN
    Mark Nelson

    University of Illinois Urbana-Champaign, United States

    1 publications · 41 citations

    1

    h-index

1–5 of 57

Venues

  1. TURKISH JOURNAL OF AGRICULTURE AND FORESTRY

    1 publications · 17 citations

    1

    h-index

  2. 1

    h-index

  3. 1

    h-index

  4. arXiv (Cornell University)

    Repository · 1 publications · 38 citations

    1

    h-index

  5. Zemdirbyste-Agriculture

    1 publications · 13 citations

    1

    h-index

1–5